Multi-output Deep-Supervised Classifier Chains for Plant Pathology

2025-07-27

AI Summary

Existing plant leaf disease classification methods fail to explicitly model the semantic correlations between plant species and disease types. Method: This paper proposes a Multi-output Deeply Supervised Classification Chain (MDS-Chain) model, built upon an enhanced VGG-16 backbone, which formalizes plant species identification and disease diagnosis as a chained multi-task learning process. A deep supervision mechanism is incorporated to enforce semantic consistency across intermediate layers. Crucially, the classification chain architecture explicitly encodes the hierarchical dependency between plant species and disease categories, thereby enhancing label correlation modeling. Results: Extensive experiments on the PlantVillage and PlantDoc benchmarks demonstrate that MDS-Chain significantly outperforms state-of-the-art single-task and multi-task baselines, achieving superior accuracy and F1-score. These results validate its effectiveness and practicality for intelligent agricultural applications.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Plant leaf disease classification is an important task in smart agriculture which plays a critical role in sustainable production. Modern machine learning approaches have shown unprecedented potential in this classification task which offers an array of benefits including time saving and cost reduction. However, most recent approaches directly employ convolutional neural networks where the effect of the relationship between plant species and disease types on prediction performance is not properly studied. In this study, we proposed a new model named Multi-output Deep Supervised Classifier Chains (Mo-DsCC) which weaves the prediction of plant species and disease by chaining the output layers for the two labels. Mo-DsCC consists of three components: A modified VGG-16 network as the backbone, deep supervision training, and a stack of classification chains. To evaluate the advantages of our model, we perform intensive experiments on two benchmark datasets Plant Village and PlantDoc. Comparison to recent approaches, including multi-model, multi-label (Power-set), multi-output and multi-task, demonstrates that Mo-DsCC achieves better accuracy and F1-score. The empirical study in this paper shows that the application of Mo-DsCC could be a useful puzzle for smart agriculture to benefit farms and bring new ideas to industry and academia.

Problem

• Classifying plant leaf diseases accurately in smart agriculture
• Studying species-disease relationships for better prediction performance
• Improving accuracy and F1-score over existing multi-label methods

Innovation

• Multi-output classifier chains for plant pathology
• Modified VGG-16 backbone with deep supervision
• Chained output layers for species-disease prediction